On clean synthetic printed text, Surya has the lowest error rates for Sinhala, while Document AI and Cloud Vision are nearly tied for Tamil; the paper also contributes a synthetic Tamil OCR dataset.
In 2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer), pages 130–134
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and Tamil
On clean synthetic printed text, Surya has the lowest error rates for Sinhala, while Document AI and Cloud Vision are nearly tied for Tamil; the paper also contributes a synthetic Tamil OCR dataset.